© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4483
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments, rulings, or disputes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fasse
    -0.52
     Regis
    -0.52
    couvrez
    -0.51
    ล้ว
    -0.50
    inematics
    -0.50
    igable
    -0.49
     adjourn
    -0.49
     gué
    -0.48
    Πηγή
    -0.48
     Salaam
    -0.47
    POSITIVE LOGITS
    AlterField
    0.62
    SharedDtor
    0.62
    WEBPACK
    0.61
    SerializedSize
    0.59
    onOptions
    0.58
    setupUi
    0.58
    Jeografia
    0.57
    +#+#
    0.57
    migrationBuilder
    0.55
    Datuak
    0.54
    Activations Density 0.941%

    No Known Activations